{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QQPJCXXQO2UNIE6XYQ2DLYXQHM","short_pith_number":"pith:QQPJCXXQ","schema_version":"1.0","canonical_sha256":"841e915ef076a8d413d7c43435e2f03b03928ebbc314b2fc6a6f299354a987fe","source":{"kind":"arxiv","id":"2412.07120","version":2},"attestation_state":"computed","paper":{"title":"Corrupted Learning Dynamics in Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.GT","authors_text":"Haipeng Luo, Shinji Ito, Taira Tsuchiya","submitted_at":"2024-12-10T02:23:44Z","abstract_excerpt":"Learning in games refers to scenarios where multiple players interact in a shared environment, each aiming to minimize their regret. An equilibrium can be computed at a fast rate of $O(1/T)$ when all players follow the optimistic follow-the-regularized-leader (OFTRL). However, this acceleration is limited to the honest regime, in which all players adhere to a prescribed algorithm -- a situation that may not be realistic in practice. To address this issue, we present corrupted learning dynamics that adaptively find an equilibrium at a rate that depends on the extent to which each player deviate"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.07120","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2024-12-10T02:23:44Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"642e5c831eb4f9429dac5a1b8c1d0e447123d37fc5a068391a4dad94c0be26f3","abstract_canon_sha256":"83755575d7b4ad37bf04fcacb059bed24fa32a5bd61baf5223b2347959d14a5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:48.828415Z","signature_b64":"r+QkwLDkGBK0J21R5Hy8r//DjeCbe8UmLFWZ0MxJBm//Gf6xAXUENnXMalsdtqIu7bIez3k4kdxw3QaE0j2lCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"841e915ef076a8d413d7c43435e2f03b03928ebbc314b2fc6a6f299354a987fe","last_reissued_at":"2026-07-05T10:14:48.827888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:48.827888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Corrupted Learning Dynamics in Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.GT","authors_text":"Haipeng Luo, Shinji Ito, Taira Tsuchiya","submitted_at":"2024-12-10T02:23:44Z","abstract_excerpt":"Learning in games refers to scenarios where multiple players interact in a shared environment, each aiming to minimize their regret. An equilibrium can be computed at a fast rate of $O(1/T)$ when all players follow the optimistic follow-the-regularized-leader (OFTRL). However, this acceleration is limited to the honest regime, in which all players adhere to a prescribed algorithm -- a situation that may not be realistic in practice. To address this issue, we present corrupted learning dynamics that adaptively find an equilibrium at a rate that depends on the extent to which each player deviate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07120","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.07120/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.07120","created_at":"2026-07-05T10:14:48.827951+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07120v2","created_at":"2026-07-05T10:14:48.827951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07120","created_at":"2026-07-05T10:14:48.827951+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQPJCXXQO2UN","created_at":"2026-07-05T10:14:48.827951+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQPJCXXQO2UNIE6X","created_at":"2026-07-05T10:14:48.827951+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQPJCXXQ","created_at":"2026-07-05T10:14:48.827951+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15454","citing_title":"Pointwise Convergence in Games with Conflicting Interest","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQPJCXXQO2UNIE6XYQ2DLYXQHM","json":"https://pith.science/pith/QQPJCXXQO2UNIE6XYQ2DLYXQHM.json","graph_json":"https://pith.science/api/pith-number/QQPJCXXQO2UNIE6XYQ2DLYXQHM/graph.json","events_json":"https://pith.science/api/pith-number/QQPJCXXQO2UNIE6XYQ2DLYXQHM/events.json","paper":"https://pith.science/paper/QQPJCXXQ"},"agent_actions":{"view_html":"https://pith.science/pith/QQPJCXXQO2UNIE6XYQ2DLYXQHM","download_json":"https://pith.science/pith/QQPJCXXQO2UNIE6XYQ2DLYXQHM.json","view_paper":"https://pith.science/paper/QQPJCXXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07120&json=true","fetch_graph":"https://pith.science/api/pith-number/QQPJCXXQO2UNIE6XYQ2DLYXQHM/graph.json","fetch_events":"https://pith.science/api/pith-number/QQPJCXXQO2UNIE6XYQ2DLYXQHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQPJCXXQO2UNIE6XYQ2DLYXQHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQPJCXXQO2UNIE6XYQ2DLYXQHM/action/storage_attestation","attest_author":"https://pith.science/pith/QQPJCXXQO2UNIE6XYQ2DLYXQHM/action/author_attestation","sign_citation":"https://pith.science/pith/QQPJCXXQO2UNIE6XYQ2DLYXQHM/action/citation_signature","submit_replication":"https://pith.science/pith/QQPJCXXQO2UNIE6XYQ2DLYXQHM/action/replication_record"}},"created_at":"2026-07-05T10:14:48.827951+00:00","updated_at":"2026-07-05T10:14:48.827951+00:00"}